Statistical Signal Processing II: Linear Estimation and Adaptive Filters

Course Description:

Unified introduction to the theory, implementation, and applications of statistical signal processing methods. Focus on optimum linear filters, Wiener filters, least squares, adaptive filters, LMS and RLS algorithms, and the Kalman filter.  Example applications in system identification, noise canceling, signal enhancement, and adaptive equalization.  Designed to give a solid foundation in the underlying theory balanced with examples of practical applications and limitations.

Course handouts:

• Syllabus
• Lecture Material:
  • Introduction - Class Overview
  • Review of Probability and Random Processes
  • Linear Estimation and Wiener Filtering - Part 1
  • Linear Estimation and Wiener Filtering - Part 2
  • Least Squares
  • Adaptive Filters Part 1 - LMS
  • Adaptive Filters Part 2 - LMS Variants
  • Adaptive Filters Part 3 - Applications
  • Adaptive Filters Part 4 - RLS
  • Discrete-Time Kalman Filtering
• Homework Assignments:
  • Homework 1 (due 10/15/15) 
  • Homework 2 (due 10/27/15) 
  • Homework 3 (due 11/5/15) 
  • Homework 4 (vegaN.wav)(due 11/12/15) 
• Projects Examples
• Important Dates:​
  • Project Presentations - 12/1 and 12/3